Every 📧

AI-pill your whole company with the Every Agent:

[Every 📧 @every]

Introducing: The @Every agent, the fastest way to AI-pill your company, now officially out of beta.

With personal agent use, no one can see how their teammates are working with AI. With one “company agent” in @SlackHQ, they can.

The Every agent comes loaded with the skills and workflows we use to run Every, and each person on your team gets $15 in free credits to try it.

Install @Every in @SlackHQ today: https://t.co/NGwMfx1f8V

[Dan Shipper @danshipper]

BREAKING:

Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.

It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.

You can try it today with $15 in free credits per person, up to $500 per workspace.

After that: it comes with your $30/month Every subscription, plus tokens at cost.

Add the Every Agent to Slack: https://t.co/L7ergneERt

Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.

The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.

Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.

Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.

In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.

This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.

That's why we made the @every agent for ourselves—and why we're releasing it to you today.

Add the Every Agent to Slack: https://t.co/L7ergneERt

[Every 📧 @every]

100 AI experiments won’t help your company if none of them land.

@kieranklaassen’s advice for frontier teams: Listen to the people doing the work, make the experiments understandable, and help the useful ones get adopted.

Dumping everything into a channel is easy. Integration is the job.

Watch the full episode: https://t.co/3zyt6JRmUb

[Every 📧 @every]

The raw material for an explainer video was already in @hammer_mt’s @SlackHQ messages and @meetgranola notes.

He asked Opus to find the narrative, pull references to what he’d said, and cut a video explaining Checks, Every’s personal benchmark product.

For someone busy running experiments, that makes it easier to tell the team what he’s been building.

Watch the full episode: https://t.co/COSuoX2RSt

[Every 📧 @every]

Before the CEO woke up, the Every Agent flagged a customer who was still waiting for their test results.

The customer, a farmer, had paid for bovine parentage testing and was asking for an update. The only issue was the engineer in charge was out sick. Thankfully, the agent’s morning report connected those facts and suggested a coworker who could cover.

That’s one example from FeanixBio, a 28-person cattle genetics startup serving about 35 family-owned farms. Its team uses the shared agent for task reports and vacation coverage, too.

Install the Every Agent: https://t.co/VHaDlNPg6A
Read more: https://t.co/kMvqkX6Gyi

[Every 📧 @every]

What would it look like to manage coding agents at the level of goals and plans?

@JannikJung built Minga to try it. He gives an orchestrator the requirements; it breaks the work into tasks, tracks dependencies, and starts work in the background.

When it needs a decision or feedback on a UI, it brings him back in.

Watch the full episode: https://t.co/F8Oa7rBeQ1

[Every 📧 @every]

AI makes it easier to generate ideas. It also makes it easier to overwhelm everyone around you.

@hammer_mt’s next job is making his experiments easier to absorb: turning the work into digestible videos and protecting his colleagues’ attention as his output grows.

Watch the full episode: https://t.co/W0Sz8uxxtL

[Every 📧 @every]

“Don’t freak out, I cloned you.”

That’s what @hammer_mt told @nataliazarina after distilling a year of her Slack messages into a natalia.md file describing how she thinks and makes decisions. He then asked an AI to use that file to critique a client email as Natalia would.

Using SynthTeam, an open-source library that turns someone’s Slack history into a persona file, he had Codex pull a year of Natalia’s messages from public channels. He looked for situations where she’d made decisions and reverse-engineered how she made them.

Read the full piece: https://t.co/EX61F7u6xD

[Every 📧 @every]

Thoughts?

[Every 📧 @every]

Getting an AI-built prototype to work once is only the beginning.

@JannikJung helps turn experiments into software the team can rely on. That means making decisions about code structure, libraries, deployment, and how the project will be maintained.

Watch the full episode: https://t.co/hSx8FgYQZk

[Every 📧 @every]

How to write well with AI: Know your reader.

@kplikethebird is adding audience.md to Compound Writing, alongside its voice.md and style.md.

For her Working Overtime column, that means checking whether a draft welcomes the AI-curious reader while giving the experienced operator enough practical detail.

Watch the full episode: https://t.co/ixg5OOwF4b

[Every 📧 @every]

ATTENDING: @deremer of @VGVentures will attend Thesis: 2027.

Apply to attend Thesis, our inaugural conference on work and AI: https://t.co/J5blFaiyMF

[Every 📧 @every]

Too many browser tabs sent @jackcheng down an unexpected path: building his own browser.

It has no tabs, an agent pane for editing with different models, and a peek mode for looking something up without losing his place.

A small example of what becomes possible when you can change the application around your workflow.

Watch the full episode: https://t.co/l3nRy3jMDJ

[Every 📧 @every]

Earlier this year, every teammate had a personal agent. Then none of us wanted to keep fixing and updating them.

So we shifted to building a shared agent, relying on @AnthropicAI’s Claude Managed Agents infrastructure. @paridhitweets helped build the first version of the Every Agent that went live within a week.

Now that the hard part was handled by Anthropic, we could focus on the parts that made the Every Agent more like a coworker: how it behaves, when it should stay quiet, and which connections each teammate can use. Security-wise, credentials stay out of the agent’s view, and changes to shared skills require human approval.

There are some trade-offs: We’re tied to Claude, and persistent conversation history means the platform doesn’t support zero-data retention.

Install the Every Agent: https://t.co/PO0SHE7gAb

Read more on our experience building the Every Agent on Claude Managed Agents: https://t.co/Pk0xJlpMIW

[Every 📧 @every]

Your AI team needs pirates and architects.

Pirates try a billion things and find what’s useful. Architects turn the promising mess into something other people can use and maintain.

At Every, @danshipper sees that handoff as the difference between a one-off experiment and a system the company can build on.

Watch the full episode: https://t.co/308Hfula1o

[Every 📧 @every]

A new AI model drops. Cool, but does it change anything about your work?

Frontier Alerts is our first answer to that question: The Every Agent uses what it knows about your tools and workflows to suggest what a new model might help you do—or tell you there’s little reason to switch.

The goal is to make a model release feel useful rather than overwhelming: You know what to try, where to use it, and when to keep working as you are.

Install the Every Agent in Slack: https://t.co/WDCOUXPyPW

[Every 📧 @every]

When understanding goes from “this is too much work” to “this changes everything” in seven minutes.

@kevinrose on why @kieranklaassen’s Compound Engineering plugin clicked instantly.

[Tyler Nishida @TylerNishida]

@hyumankind use artifacts to show you multiple layouts + product questions that you should answer

ask claude to make a video of the flow or concept (with the cursor moving and click/tap)

make personal tools. i made one to learn origami and another to quiz me on my draft PRs

[Kieran Klaassen @kieranklaassen]

I am working on the Frontier at @every
Meet the team and more!

[Randy Counsman @RandyCounsman]

The frontier team is easily one of the coolest within @every and @kieranklaassen is like the frontieriest of the frontier

[Every 📧 @every]

@interplato @danshipper @AnthropicAI working on it!

[Francesco Oddo | AI Arc @oxfrancesco_]

Give a raise to the @every designer!